7/11/2014

Mixture of Gaussian code is running very very slow. - MATLAB Answers - MATLAB Central
Search:

Answers
Create Account

File Exchange

Answ ers

New sgroup

Link Exchange

Blogs

Trendy

Cody

Contest

Log In

MathWorks.com

Mixture of Gaussian code is running very very slow.

Asked by Duke Watson on 30 May 2012

MATLAB and Simulink

resources for Arduino, LEGO,
and Raspberry Pi
Learn more

Here I am pasting my code. Plz tell me if there is any correction to work it fast.......
% This m-file implements the mixture of Gaussians algorithm for background
% subtraction. It may be used free of charge for any purpose (commercial
% or otherwise), as long as the author (Seth Benton) is acknowledged.
clear all
% source = aviread('C:\Video\Source\traffic\san_fran_traffic_30sec_QVGA');
%source = aviread('..\test_video\san_fran_traffic_30sec_QVGA_Cinepak');
[FileName, PathName] = uigetfile('*.avi', 'Pick an avi-file');
source= aviread(strcat(PathName, FileName));
% ----------------------- frame size variables ----------------------fr = source(1).cdata;
% read in 1st frame as background frame
fr_bw = rgb2gray(fr);
% convert background to greyscale
fr_size = size(fr);
width = fr_size(2);
height = fr_size(1);
fg = zeros(height, width);
bg_bw = zeros(height, width);
% --------------------- MOG variables ----------------------------------C = 3;
% number of gaussian components (typically 3-5)
M = 3;
% number of background components
D = 2.5;
% positive deviation threshold
alpha = 0.10;
% learning rate (between 0 and 1) (from paper 0.01)
thresh = 0.25;
% foreground threshold (0.25 or 0.75 in paper)
sd_init = 6;
% initial standard deviation (for new components) var = 36 in
paper
w = zeros(height,width,C);
% initialize weights array
mean = zeros(height,width,C);
% pixel means
sd = zeros(height,width,C);
% pixel standard deviations
u_diff = zeros(height,width,C);
% difference of each pixel from mean
p = alpha/(1/C);
% initial p variable (used to update mean and sd)
rank = zeros(1,C);
% rank of components (w/sd)
%cmap = rand(236, 3);
%Mov1=zeros(length(source));
%preallocating the array for Mov1
%Mov2=zeros(length(source));
%preallocating the array for Mov2
% --------------------- initialize component means and weights ----------pixel_depth = 8;
pixel_range = 2^pixel_depth -1;

% 8-bit resolution
% pixel range (# of possible values)

for i=1:height
for j=1:width
for k=1:C
mean(i,j,k) = rand*pixel_range;
w(i,j,k) = 1/C;
sd(i,j,k) = sd_init;

end

end

% means random (0-255)

% weights uniformly dist
% initialize to sd_init

end

%--------------------- process frames ----------------------------------for n = 1:length(source)

fr = source(n).cdata;
fr_bw = rgb2gray(fr);

% read in frame
% convert frame to grayscale

% calculate difference of pixel values from mean

for m=1:C
u_diff(:,:,m) = abs(double(fr_bw) - double(mean(:,:,m)));
end
% update gaussian components for each pixel
for i=1:height
for j=1:width
match = 0;
for k=1:C
if (abs(u_diff(i,j,k)) <= D*sd(i,j,k))
match = 1;

% pixel matches component

% variable to signal component match

% update weights, mean, sd, p

w(i,j,k) = (1-alpha)*w(i,j,k) + alpha;
p = alpha/w(i,j,k);
mean(i,j,k) = (1-p)*mean(i,j,k) + p*double(fr_bw(i,j));
sd(i,j,k) = sqrt((1-p)*(sd(i,j,k)^2) + p*((double(fr_bw(i,j)) - mean(i,j,k)))^2);
else
% pixel doesn't match component
w(i,j,k) = (1-alpha)*w(i,j,k);
% weight slighly decreases
end

end

w(i,j,:) = w(i,j,:)./sum(w(i,j,:));
bg_bw(i,j)=0;
for k=1:C
bg_bw(i,j) = bg_bw(i,j)+ mean(i,j,k)*w(i,j,k);
end
% if no components match, create new component
if (match == 0)
[min_w, min_w_index] = min(w(i,j,:));
mean(i,j,min_w_index) = double(fr_bw(i,j));
sd(i,j,min_w_index) = sd_init;

http://www.mathworks.in/matlabcentral/answers/39790-mixture-of-gaussian-code-is-running-very-very-slow

1/3

7/11/2014

Mixture of Gaussian code is running very very slow. - MATLAB Answers - MATLAB Central
end
rank = w(i,j,:)./sd(i,j,:);
rank_ind = [1:1:C];

% calculate component rank

% sort rank values

for k=2:C
for m=1:(k-1)
if (rank(:,:,k) > rank(:,:,m))
% swap max values
rank_temp = rank(:,:,m);
rank(:,:,m) = rank(:,:,k);
rank(:,:,k) = rank_temp;
% swap max index values
rank_ind_temp = rank_ind(m);
rank_ind(m) = rank_ind(k);
rank_ind(k) = rank_ind_temp;

end

end

end

% calculate foreground
match = 0;
k=1;
fg(i,j) = 0;
while ((match == 0)&&(k<=m))

end

end

end

if (w(i,j,rank_ind(k)) >= thresh)

if (abs(u_diff(i,j,rank_ind(k))) <= D*sd(i,j,rank_ind(k)))
fg(i,j) = 0;
match = 1;
else
fg(i,j) = fr_bw(i,j);
end
end
k = k+1;

figure(1),subplot(3,1,1),imshow(fr)
subplot(3,1,2),imshow(uint8(bg_bw))
subplot(3,1,3),imshow(uint8(fg))
Mov1(n) = im2frame(uint8(fg),gray);
Mov2(n) = im2frame(uint8(bg_bw),gray);

% put frames into movie

% put frames into movie

end
movie2avi(Mov1,'mixture_of_gaussians_output','fps',50);
movie2avi(Mov2,'mixture_of_gaussians_background','fps',50);

% save movie as avi

% save movie as avi

4 Comments
Show 1 older comment
Walter Roberson on 30 May 2012
Link

Direct link to this comment:

http://www.mathworks.in/matlabcentral/answers/39790#comment_82254
step #0: get rid of the "clear all".
Duke Watson on 30 May 2012
Link

Direct link to this comment:

http://www.mathworks.in/matlabcentral/answers/39790#comment_82258
Yeah i have done that but still the problem of video is same. It is running very slow. You can test this code on your pc
Ahmed on 1 Apr 2013
Link

Direct link to this comment:

http://www.mathworks.in/matlabcentral/answers/39790#comment_140367
@Duke Watson, did you come up with the solution for the speed? please let me know
Algorithms Analyst on 1 Apr 2013
Link

Direct link to this comment:

http://www.mathworks.in/matlabcentral/answers/39790#comment_140369
Apply matlab parallel computing toolbox...
like matlab pool open

0 votes

Tags
preallocating mov1

http://www.mathworks.in/matlabcentral/answers/39790-mixture-of-gaussian-code-is-running-very-very-slow

2/3

7/11/2014

Mixture of Gaussian code is running very very slow. - MATLAB Answers - MATLAB Central
Products
MATLAB

0 Answers
Contact us

1994-2014 The MathWorks, Inc.

Site Help
Featured MathWorks.com Topics:

Patents

Trademarks

Privacy Policy

New Products

Support

Documentation

http://www.mathworks.in/matlabcentral/answers/39790-mixture-of-gaussian-code-is-running-very-very-slow

Preventing Piracy
Training

Terms of Use

Webinars

Newsletters

MATLAB Trials

Careers

3/3